Skip to main content
Glama

TradeHub

by net.tichat.tradehub
OverviewDiscussionsAdmin

My performance

get_my_agent_performance
Read-onlyIdempotent

How this agent has done: trades, wins, realised profit or loss in USD, its most common refusals with what to do differently (last N days), and real_money: whether its sandbox record is ready for real money. Use at the start of a session, after rejections, or when asked about trading real money. Not for the trades themselves (use get_my_trade_history). Input: days (1-90). Only a person promotes an agent, on TradeHub Web. Next: get_my_trading_permissions.

Input Schema

NameRequiredDescriptionDefault
daysNoLook-back window in days

Output Schema

NameRequiredDescriptionDefault
daysYesWindow, in days
winsYesClosed with a profit
closedYesOf those, closed
tradesYesPositions opened in the window
refusedYesRefused previews or executions
agent_idYesThis agent (null: a person, all agents together)
refusalsYesMost common refusals first
win_rateYeswins / closed, as a fraction
real_moneyNoAgents only: whether its sandbox record is ready for real money. Only a person promotes an agent, on TradeHub Web
deprecationNoPresent only while this tool is deprecated: replacement, removal_date, changelog
order_callsYesPreviews and refusals
average_pnl_usdYesrealized_pnl_usd / closed, USD
realized_pnl_usdYesSum of realised profit or loss, USD
fixed_within_3_callsYesRefusals the agent should fix itself (error.who = agent) followed by a successful preview within the next 3 calls

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / $defs / Criterion
      Added value: +{
+  "additionalProperties": true,
+  "properties": {
+    "deprecation": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "Present only while this tool is deprecated: replacement, removal_date, changelog",
+      "title": "Deprecation"
+    },
+    "met": {
+      "description": "True: this line is met",
+      "title": "Met",
+      "type": "boolean"
+    },
+    "name": {
+      "description": "days, closed_trades, net_pnl_usd, max_drawdown_pct, with_stop_pct or auto_pauses_7d",
+      "title": "Name",
+      "type": "string"
+    },
+    "need": {
+      "description": "The bar: a minimum, or a maximum for max_drawdown_pct and auto_pauses_7d",
+      "title": "Need",
+      "type": "number"
+    },
+    "value": {
+      "description": "This agent's sandbox record",
+      "title": "Value",
+      "type": "number"
+    }
+  },
+  "required": [
+    "name",
+    "value",
+    "need",
+    "met"
+  ],
+  "title": "Criterion",
+  "type": "object"
+}
    • addedOutput schema / $defs / Probation
      Added value: +{
+  "additionalProperties": true,
+  "properties": {
+    "deprecation": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "Present only while this tool is deprecated: replacement, removal_date, changelog",
+      "title": "Deprecation"
+    },
+    "loss_limit_usd": {
+      "description": "Realised loss on that venue that sends it back to the sandbox",
+      "title": "Loss Limit Usd",
+      "type": "number"
+    },
+    "loss_so_far_usd": {
+      "description": "Realised loss on that venue since the promotion",
+      "title": "Loss So Far Usd",
+      "type": "number"
+    },
+    "status": {
+      "description": "active, demoted (lost loss_limit_usd and went back to the sandbox) or ended",
+      "title": "Status",
+      "type": "string"
+    },
+    "until": {
+      "description": "ISO 8601 UTC end of the probation",
+      "title": "Until",
+      "type": "string"
+    },
+    "venue": {
+      "description": "The real venue it was promoted to",
+      "title": "Venue",
+      "type": "string"
+    }
+  },
+  "required": [
+    "venue",
+    "status",
+    "loss_limit_usd",
+    "loss_so_far_usd",
+    "until"
+  ],
+  "title": "Probation",
+  "type": "object"
+}
    • addedOutput schema / $defs / RealMoney
      Added value: +{
+  "additionalProperties": true,
+  "properties": {
+    "criteria": {
+      "description": "Its sandbox record (last 90 days) against the bar for real money",
+      "items": {
+        "$ref": "#/$defs/Criterion"
+      },
+      "title": "Criteria",
+      "type": "array"
+    },
+    "deprecation": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "Present only while this tool is deprecated: replacement, removal_date, changelog",
+      "title": "Deprecation"
+    },
+    "missing": {
+      "description": "Lines not met yet",
+      "items": {
+        "type": "string"
+      },
+      "title": "Missing",
+      "type": "array"
+    },
+    "probation": {
+      "anyOf": [
+        {
+          "$ref": "#/$defs/Probation"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "The latest promotion, if any"
+    },
+    "ready": {
+      "description": "True: its sandbox record meets every line below",
+      "title": "Ready",
+      "type": "boolean"
+    },
+    "trades_real_venues": {
+      "description": "True: its mandate already includes a real venue (or one is waiting to apply)",
+      "title": "Trades Real Venues",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "trades_real_venues",
+    "ready",
+    "missing",
+    "criteria"
+  ],
+  "title": "RealMoney",
+  "type": "object"
+}
    • addedOutput schema / properties / real_money
      Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/RealMoney"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Agents only: whether its sandbox record is ready for real money. Only a person promotes an agent, on TradeHub Web"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context beyond them: the refusal analysis with suggested fixes, the real-money readiness signal, and the note that only a person promotes an agent via TradeHub Web. It does not cover pagination or response-size behavior, but those are less critical for a read-only summary with an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded: purpose first, then when to use it, exclusion, parameter note, domain constraint, and next tool. Every sentence carries actionable information, with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a read-only summary tool with one optional parameter and an output schema, the description is complete. It covers use cases, exclusions, the lookback input, the promotion constraint, and the follow-up tool, leaving no critical decision unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the single days parameter is already fully described by the schema. The description's 'Input: days (1-90)' repeats the schema's min/max without adding format or behavioral detail. This is the expected baseline when the schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and scope: an agent performance summary covering trades, wins, realised P&L, common refusals, and real-money readiness. It explicitly distinguishes itself from get_my_trade_history, which is the sibling for the underlying trades.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear triggers: start of session, after rejections, or when asked about trading real money. It also names the exclusion case and points to get_my_trade_history, then recommends get_my_trading_permissions as the next step.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TradeHub toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources